Abstract: A memory embodies instructions, and a processor is coupled to the memory and is operative by the instructions to facilitate: accessing a source of information regarding farm cultivation techniques; constructing a cultivation knowledge graph by parsing the source of information regarding farm cultivation techniques, using natural language processing; identifying cultivation quality assessment factors by applying machine learning to the cultivation knowledge graph; estimating quality of a farm cultivation task by comparing a stream of real-time data to the cultivation quality assessment factors, wherein the stream of real-time data is related to performance of the farm cultivation task; identifying from the stream of real-time data, using the cultivation knowledge graph, a controllable variable that affects the quality of the farm cultivation task; and improving the quality of the farm cultivation task by facilitating a change in the controllable variable.

Abstract: An information processing system according to one embodiment includes: a provision unit configured to transmit to a user terminal an incentive list indicating one or more incentives provided by one or more facilities; a receiving unit configured to receive from the user terminal an incentive selected from the incentive list by a user of the user terminal; and a request unit configured to transmit a reservation request for reserving a power transmitting device of a corresponding facility which is the facility corresponding to the selected incentive for a vehicle corresponding to the user, to the corresponding facility.

Abstract: A method for analyzing a fluid of a pool by a floating system. The method may include sensing, by a sensor of the floating system, at least one out of (a) a wind parameter related to a wind that impinges on the floating system and (b) a movement of the floating system; wherein the floating system further comprises a top portion comprises at least one float, a submerged portion that comprises comprises a fluid analysis instrument, a power source, a controller, and a propulsion unit; determining, by the controller, an impact of the wind on the floating system based on the at least one out of the wind parameter and the movement of the floating system; controlling, by the controller, a movement of the floating system based, at least in part, on the impact of the wind; and analyzing, by the fluid analysis instrument, at one or more analysis points, the fluid of the pool to provide one or more fluid analysis results.

Abstract: Disclosed is a solution to the use of a speed limiter in a motorcycle that has a high capacity for acceleration, including a method for limiting the speed of a motorcycle using precise parameters of speed, acceleration and required engine torque and a single control button to manage the smart activation and deactivation of the limiter and to input new speed limits Vlim in a simple way. It thus allows the use of a speed-limiting system in a motorcycle that has a high power/weight ratio by avoiding the sources of interference with the riding and the effects liable to jeopardize its stability.

Abstract: An example method for assisting autonomous vehicle (AV) riders reach their destination after drop-off can include navigating the AV to a drop-off location associated with a user in the AV, receiving sensor data from sensors associated with the AV, determining, based on the sensor data, an orientation of the user in the AV and a location of the AV relative to a final destination of the user, generating a recommendation for how to exit the AV at the drop-off location based on the orientation of the user in the AV and the location of the AV relative to the final destination of the user, and providing the recommendation via a display, a speaker, a light-emitting device, and/or a client device, the recommendation including a visual indication of an exit direction or an AV door to use to exit the AV, audio instructions for exiting the AV, and/or visual exit instructions.

Abstract: In various examples, systems and methods are disclosed that accurately identify driver and passenger in-cabin activities that may indicate a biomechanical distraction that prevents a driver from being fully engaged in driving a vehicle. In particular, image data representative of an image of an occupant of a vehicle may be applied to one or more deep neural networks (DNNs). Using the DNNs, data indicative of key point locations corresponding to the occupant may be computed, a shape and/or a volume corresponding to the occupant may be reconstructed, a position and size of the occupant may be estimated, hand gesture activities may be classified, and/or body postures or poses may be classified. These determinations may be used to determine operations or settings for the vehicle to increase not only the safety of the occupants, but also of surrounding motorists, bicyclists, and pedestrians.

Abstract: A computing system computes a timing interval between high-capacity vehicles (HCVs) for each HCV corridor within a geographic region to control rates of HCVs entering and exiting each of the HCV corridors. For each of the HCV corridors, the computing system schedules a first HCV to provide a transport service along the corridor beginning at a first starting time, transmits first schedule data for the corridor to the first HCV, schedules a second HCV to provide the transport service along the corridor beginning at a second starting time after the first starting time according to the timing interval for the corridor, and transmits second schedule data for the corridor to the second HCV.

Abstract: Embodiments of the present disclosure disclose a method for calibrating a relative pose, a device, and a medium. The method includes: obtaining first point cloud data of a scene collected by the laser radar in an automatic driving mobile carrier and first pose data collected by the navigation positioning system in the automatic driving mobile carrier; and determining the relative pose between the laser radar and the navigation positioning system based on the first point cloud data, the first pose data, second point cloud data pre-collected by a laser scanner in the scene and second pose data pre-collected by a positioning device in the scene.

Abstract: Embodiments of the invention include a vehicle telematics system including a telematics device, wherein the telematics device detects, using a processor of a telematics device, a vehicle ignition off event and reconfigures at least one parameter of an accelerometer for a low power mode of operation while in the vehicle ignition off state, and places the telematics device in a sleep mode of operation, wherein an accelerometer generates an interrupt to wake the processor of the telematics device from the sleep mode of operation upon detecting an acceleration event that exceeds a threshold, and the processor of the telematics device analyzes the accelerometer data stored in a FIFO buffer of the accelerometer.

Abstract: A computer-implemented method of using telematics data associated with an originating vehicle at a destination vehicle is provided. The method may include receiving telematics data associated with the originating vehicle by (1) a mobile device or (2) a smart vehicle controller associated with a driver or vehicle. The mobile device or smart vehicle controller may analyze the telematics data received to determine that (i) a travel event exists, or (ii) that a travel event message or warning is embedded within the telematics broadcast received. If the travel event exits, the method may include automatically taking a preventive or corrective action, at or via the mobile device or smart vehicle controller, which alleviates a negative impact of the travel event on the driver or vehicle to facilitate safer or more efficient vehicle travel. Insurance discounts may be provided to insureds based upon their usage of the risk mitigation or prevention functionality.

Abstract: An autobrake brake control system includes a shutoff valve configured to receive a hydraulic fluid, a servo valve configured to receive the hydraulic fluid from the shutoff valve and configured to provide the hydraulic fluid to apply braking force to a wheel via a hydraulic line, and a brake control unit in electronic communication with the shutoff valve. The brake control unit is configured to detect a weight-on-wheel (WOW) condition of a nose landing gear, and the brake control unit controls the shutoff valve in response to detecting the WOW condition of the nose landing gear.

Abstract: A power supply system includes a high voltage circuit; a system ECU that controls the high voltage circuit; and a backup power supply unit that supplies electric power in the high voltage circuit to the system ECU. The system ECU includes a discharge controller that performs discharge control to discharge the electric charges in a smoothing capacitor until a secondary-side voltage is reduced to a discharge termination determination voltage or lower; and a vehicle state monitor that determines whether a vehicle is in a stopped state, and determines whether the secondary-side voltage is lower than or equal to a re-rise determination voltage in a monitoring period from termination of the discharge control until the vehicle is determined to be in the stopped state. When the secondary-side voltage is determined to be higher than the re-rise determination voltage by the vehicle state monitor, the discharge controller performs the discharge control again.

Abstract: Technologies for drone-based cameras to detect proper wind direction for landing are described. One aerial vehicle can determine that it is in a vertical take-off and landing (VTOL) orientation and capture an image of a landing-pad device using the camera. The aerial vehicle can detect a visual marker in the image and can determine a wind direction, at a location of the landing page, from the visual marker. The wind direction is used by a propulsion subsystem to align the aerial vehicle into the wind direction for landing.

Abstract: An autonomous driving vehicle (ADV) receives instructions for a human test driver to drive the ADV in manual mode and to collect a specified amount of driving data for one or more specified driving categories. As the user drivers the ADV in manual mode, driving data corresponding to the one or more driving categories is logged. A user interface of the ADV displays the one or more driving categories that the human driver is instructed collect data upon, and a progress indicator for each of these categories as the human driving progresses. The driving data is uploaded to a server for machine learning. If the server machine learning achieves a threshold grading amount of the uploaded data to variables of a dynamic self-driving model, then the server generates an ADV self-driving model, and distributes the model to one or more ADVs that are navigated in the self-driving mode.

Abstract: Techniques are discussed for determining a data level for portions of data for processing. In some cases, a data level can correspond to a resolution level, a compression level, a bit rate, and the like. In the context of image data, the techniques can determine a region of first image data to be processed a high resolution and a region of second image data to be processed at a low resolution. The regions can be determined by a machine learned algorithm that is trained to output identifications of such regions. Training data may be determined by identifying differences in outputs based on the first and second image data. The image data associated with the determined regions and the determined resolutions can be processed to perform object detection, classification, segmentation, bounding box generation, and the like, thereby conserving processing, bandwidth, and/or memory resources in real time systems.

Abstract: The present invention is provided with: a sensing unit which is provided in a vehicle and measures the three-dimensional shape of an object; a matching unit for performing matching between multiple sets of structure information, in which are associated a data group indicating the three-dimensional shapes of structures provided beforehand near a path the vehicle will travel along and positional information indicating the posit ions of the structures, and a data group indicating the three-dimensional shape of the object measured by the sensing unit, and for specifying the position of the object; and an estimated position determination unit for determining, with the position specified by the matching unit as a reference position, the estimated position of the vehicle on the basis of the reference position.

Abstract: A method includes obtaining multiple sets of trajectory data, each descriptive of trajectories of two or more objects (e.g., first and second objects). The method also includes generating transformed trajectory data based on the trajectory data. Each set of transformed trajectory data is descriptive of the trajectories of the two or more objects in a normalized reference frame in which a movement path of the first object is constrained. The method further includes generating feature data, performing a clustering operation based on the feature data to generate a set of trajectory clusters, and generating training data based on the set of trajectory clusters. The method further includes using the training data to train a machine learning classifier to classify particular trajectory patterns.

Abstract: A method for determining misalignment of a vehicular camera includes equipping a vehicle with a vehicular vision system having an electronic control unit and a plurality of cameras disposed at the vehicle so that each camera has a respective field of view exterior of the vehicle. Responsive to processing at the electronic control unit of received vehicle data during driving of the vehicle, the vehicular vision system determines a vehicle motion vector during driving of the vehicle. Frames of image data captured by the plurality of cameras are processed to determine an object motion vector of a detected object based on positions of the detected object in frames of image data captured by the camera. The determined object motion vector is compared to the determined vehicle motion vector to determine via the vehicular vision system that the camera of the plurality of cameras is misaligned.

Abstract: A computer that includes a processor and memory storing instructions executable by the processor. The computer may be programmed to: determine feature-selection data; determine that a mobile device is within a proximity threshold of a vehicle; and in response to the determinations, control a vehicle display in accordance with the feature-selection data.

Abstract: A trailed vehicle comprises a cargo area, a wheeled axle assembly supporting the cargo area, a hitch assembly configured to secure the trailed vehicle to a tow vehicle, and a weight sensing system comprising a weight processing module and a user interface. The weight processing module comprises a processor and non-transitory computer readable storage comprising instructions that, when executed by the processor, cause the weight processing module to execute an axle-specific vehicle weight determination, an axle-specific vehicle weight display presented at the user interface, a hitch-specific vehicle weight determination, a hitch-specific vehicle weight display presented at the user interface, a hitch-specific weight percentage determination, a hitch-specific weight percentage display presented at the user interface, a total weight determination, a total weight display presented at the user interface, an available cargo weight determination, and an available cargo weight display presented at the user interface.